More fixes to examples

xli15 · Aug 26, 2019 · e3ca5d6 · e3ca5d6
1 parent 1636ede
commit e3ca5d6
Show file tree

Hide file tree

Showing 6 changed files with 7 additions and 22 deletions.
diff --git a/examples/muv/muv_tf.py b/examples/muv/muv_tf.py
@@ -21,7 +21,7 @@
 metric = dc.metrics.Metric(
     dc.metrics.roc_auc_score, np.mean, mode="classification")
 
-rate = dc.models.tensorgraph.optimizers.ExponentialDecay(0.001, 0.8, 1000)
+rate = dc.models.optimizers.ExponentialDecay(0.001, 0.8, 1000)
 model = dc.models.MultitaskClassifier(
     len(muv_tasks),
     n_features=1024,

diff --git a/examples/nci/nci_rf.py b/examples/nci/nci_rf.py
@@ -8,7 +8,7 @@
 import os
 import numpy as np
 import shutil
-from nci_datasets import load_nci
+from deepchem.molnet import load_nci
 from sklearn.linear_model import LogisticRegression
 from sklearn.ensemble import RandomForestRegressor
 from deepchem.data import Dataset
@@ -23,28 +23,19 @@
 # Set some global variables up top
 verbosity = "high"
 
-base_dir = "/tmp/nci_rf"
-model_dir = os.path.join(base_dir, "model")
-if os.path.exists(base_dir):
-  shutil.rmtree(base_dir)
-os.makedirs(base_dir)
-
-nci_tasks, nci_dataset, transformers = load_nci(
-    base_dir)
+nci_tasks, nci_dataset, transformers = load_nci()
 
 (train_dataset, valid_dataset, test_dataset) = nci_dataset
 
 classification_metric = Metric(metrics.roc_auc_score, np.mean,
-                               verbosity=verbosity,
                                mode="classification")
 def model_builder(model_dir):
   sklearn_model = RandomForestRegressor(n_estimators=500)
   return SklearnModel(sklearn_model, model_dir)
-model = SingletaskToMultitask(nci_tasks, model_builder, model_dir)
+model = SingletaskToMultitask(nci_tasks, model_builder)
 
 # Fit trained model
 model.fit(train_dataset)
-model.save()
 
 train_evaluator = Evaluator(model, train_dataset, transformers, verbosity=verbosity)
 train_scores = train_evaluator.compute_model_performance([classification_metric])

diff --git a/examples/pcba/pcba_tf.py b/examples/pcba/pcba_tf.py
@@ -37,7 +37,6 @@
 
 # Fit trained model
 model.fit(train_dataset)
-model.save()
 
 train_evaluator = Evaluator(model, train_dataset, transformers)
 train_scores = train_evaluator.compute_model_performance([metric])

diff --git a/examples/pdbbind/pdbbind_atomic_conv.py b/examples/pdbbind/pdbbind_atomic_conv.py
@@ -27,8 +27,7 @@
 frag1_num_atoms = 70  # for ligand atoms
 frag2_num_atoms = 24000  # for protein atoms
 complex_num_atoms = frag1_num_atoms + frag2_num_atoms
-atomic_convnet = atomic_conv.AtomicConvModel(
-    batch_size=batch_size,
+model = dc.models.AtomicConvModel(
     frag1_num_atoms=frag1_num_atoms,
     frag2_num_atoms=frag2_num_atoms,
     complex_num_atoms=complex_num_atoms)

diff --git a/examples/pdbbind/pdbbind_rf.py b/examples/pdbbind/pdbbind_rf.py
@@ -24,16 +24,12 @@
 
 metric = dc.metrics.Metric(dc.metrics.pearson_r2_score)
 
-current_dir = os.path.dirname(os.path.realpath(__file__))
-model_dir = os.path.join(current_dir, "%s_%s_RF" % (split, subset))
-
 sklearn_model = RandomForestRegressor(n_estimators=500)
-model = dc.models.SklearnModel(sklearn_model, model_dir=model_dir)
+model = dc.models.SklearnModel(sklearn_model)
 
 # Fit trained model
 print("Fitting model on train dataset")
 model.fit(train_dataset)
-model.save()
 
 print("Evaluating model")
 train_scores = model.evaluate(train_dataset, [metric], transformers)
@@ -44,3 +40,4 @@
 
 print("Validation scores")
 print(valid_scores)
+
diff --git a/examples/pdbbind/pdbbind_tf.py b/examples/pdbbind/pdbbind_tf.py
@@ -42,7 +42,6 @@
 
 # Fit trained model
 model.fit(train_dataset, nb_epoch=100)
-model.save()
 
 print("Evaluating model")
 train_scores = model.evaluate(train_dataset, [metric], transformers)